Driver Drowsiness Detection
Year: 2025
Type: article
Abstract: Drowsy driving is a leading cause of road accidents, posing significant risks to drivers and passengers. This paper presents a real-time driver drowsiness detection system that monitors facial features to identify signs of fatigue. The system utilizes computer vision techniques, specifically Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR), to detect prolonged eye closure and yawning. A webcam captures live video, and the frames are processed using Python, OpenCV, and Dlib to track facial landmarks. When drowsiness is detected, an audio alert is triggered to warn the driver. The proposed system is non-intrusive, cost-effective, and can be integrated into vehicles for enhanced safety. Future improvements may incorporate machine learning models for greater accuracy and adaptability to different environments. Key Words: Drowsiness detection, computer vision, Eye Aspect Ratio, OpenCV, real-time monitoring, driver safety.
DOI: 10.55041/ijsrem43459
Language: English
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4409000820